NVIDIA AI & NIMopen-weight
Released: 2026-06-04Artificial AnalysisNemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Intelligence Index
11.8/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
203tok/sec
Output streaming throughputTime to First Answer
4.9s
Time to first answer token, including any thinkingCost to Run the Index
2.21USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of Nemotron 3 Ultra (Reasoning configuration). Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- 11.8
- Cost to run the Index
- $2.21
- Time per task
- 4.2 min
- Omniscience index
- 3.4
- Reasoning model
- Yes
- Cached-input price
- $0.12 / 1M
Reasoning & knowledge
- AA-Omniscience Accuracy21.2%
- CritPt3.1%
- CritPt v2 (Hard)15.0%
- GPQA Diamond86.7%
- HLE-Diamond8.5%
- Humanity's Last Exam28.4%
- IFBench81.4%
Coding & terminal agents
- FrontierCode 1.110.5%
- FrontierCode-AA 2.01.1%
- SciCode40.3%
- Terminal-Bench 2.153.9%
- Terminal-Bench 4.00.5%
- Terminal-Bench Hard36.4%
- Terminal-Bench-Science 0.10.0%
Agentic work
- AA-AnalystAgent6.3%
- AA-Briefcase v1.1 (Elo)878 Elo
- AutomationBench-AA3.0%
- EnterpriseOps-Gym-AA28.9%
- GDPval-AA (normalized Elo)1020 Elo
- τ²-Bench Telecom83.3%
- τ³-Banking14.2%
Long context & documents
Multimodal & science
- AA-3D (Elo)583 Elo
- Code2Video-AA (Elo)304 Elo
Health & safety
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Reasoning · CritPt v2 (Hard)15.0%
Coding & agents · Terminal-Bench 4.00.5%
Long context · AA-LCR79.3%
Knowledge · Humanity's Last Exam28.4%
Instruction following · IFBench81.4%
Sourced Benchmark Evaluations (23)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| AA-LCR (Long Context Reasoning) | Active | 79.3% | 93 | 2026-11-15 | independent | Source ↗ |
| EnterpriseOps-Gym-AA | Active | 28.9% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-AnalystAgent | Active | 6.3% | 93 | 2026-11-15 | independent | Source ↗ |
| AutomationBench-AA | Active | 3% | 93 | 2026-11-15 | independent | Source ↗ |
| MLCR-AA (Medical Long Context Reasoning) | Active | 5.6% | 93 | 2026-11-15 | independent | Source ↗ |
| GDP.pdf | Active | 5% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode-AA 2.0 | Active | 1.1% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Non-Hallucination) | Active | 77.4% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-Omniscience (Accuracy) | Active | 21.2% | 93 | 2026-11-15 | independent | Source ↗ |
| HLE-Diamond | Active | 8.5% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt v2 (Hard) | Active | 15% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 3.1% | 93 | 2026-11-15 | independent | Source ↗ |
| FrontierCode | Active | 10.5% | 98 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench-Science 0.1 | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 4.0 | Active | 0.5% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench 2.1 | Active | 53.9% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench Hard | Active | 36.4% | 93 | 2026-11-15 | independent | Source ↗ |
| τ³-Banking | Active | 14.2% | 93 | 2026-11-15 | independent | Source ↗ |
| τ²-Bench Telecom | Active | 83.3% | 93 | 2026-11-15 | independent | Source ↗ |
| SciCode | Active | 40.3% | 93 | 2026-11-15 | independent | Source ↗ |
| IFBench | Active | 81.4% | 93 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 28.4% | 93 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 86.7% | 78 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run nvidia-nemotron-3-ultra
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia-nemotron-3-ultra",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Nemotron 3 Ultra represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.